Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-03-25

We've added 38 non-merge commits during the last 13 day(s) which contain
a total of 50 files changed, 867 insertions(+), 274 deletions(-).

The main changes are:

1) Add the ability to specify and retrieve BPF cookie also for raw
   tracepoint programs in order to ease migration from classic to raw
   tracepoints, from Andrii Nakryiko.

2) Allow the use of bpf_get_{ns_,}current_pid_tgid() helper for all
   program types and add additional BPF selftests, from Yonghong Song.

3) Several improvements to bpftool and its build, for example, enabling
   libbpf logs when loading pid_iter in debug mode, from Quentin Monnet.

4) Check the return code of all BPF-related set_memory_*() functions during
   load and bail out in case they fail, from Christophe Leroy.

5) Avoid a goto in regs_refine_cond_op() such that the verifier can
   be better integrated into Agni tool which doesn't support backedges
   yet, from Harishankar Vishwanathan.

6) Add a small BPF trie perf improvement by always inlining
   longest_prefix_match, from Jesper Dangaard Brouer.

7) Small BPF selftest refactor in bpf_tcp_ca.c to utilize start_server()
   helper instead of open-coding it, from Geliang Tang.

8) Improve test_tc_tunnel.sh BPF selftest to prevent client connect
   before the server bind, from Alessandro Carminati.

9) Fix BPF selftest benchmark for older glibc and use syscall(SYS_gettid)
   instead of gettid(), from Alan Maguire.

10) Implement a backward-compatible method for struct_ops types with
    additional fields which are not present in older kernels,
    from Kui-Feng Lee.

11) Add a small helper to check if an instruction is addr_space_cast
    from as(0) to as(1) and utilize it in x86-64 JIT, from Puranjay Mohan.

12) Small cleanup to remove unnecessary error check in
    bpf_struct_ops_map_update_elem, from Martin KaFai Lau.

13) Improvements to libbpf fd validity checks for BPF map/programs,
    from Mykyta Yatsenko.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (38 commits)
  selftests/bpf: Fix flaky test btf_map_in_map/lookup_update
  bpf: implement insn_is_cast_user() helper for JITs
  bpf: Avoid get_kernel_nofault() to fetch kprobe entry IP
  selftests/bpf: Use start_server in bpf_tcp_ca
  bpf: Sync uapi bpf.h to tools directory
  libbpf: Add new sec_def "sk_skb/verdict"
  selftests/bpf: Mark uprobe trigger functions with nocf_check attribute
  selftests/bpf: Use syscall(SYS_gettid) instead of gettid() wrapper in bench
  bpf-next: Avoid goto in regs_refine_cond_op()
  bpftool: Clean up HOST_CFLAGS, HOST_LDFLAGS for bootstrap bpftool
  selftests/bpf: scale benchmark counting by using per-CPU counters
  bpftool: Remove unnecessary source files from bootstrap version
  bpftool: Enable libbpf logs when loading pid_iter in debug mode
  selftests/bpf: add raw_tp/tp_btf BPF cookie subtests
  libbpf: add support for BPF cookie for raw_tp/tp_btf programs
  bpf: support BPF cookie in raw tracepoint (raw_tp, tp_btf) programs
  bpf: pass whole link instead of prog when triggering raw tracepoint
  bpf: flatten bpf_probe_register call chain
  selftests/bpf: Prevent client connect before server bind in test_tc_tunnel.sh
  selftests/bpf: Add a sk_msg prog bpf_get_ns_current_pid_tgid() test
  ...
====================

Link: https://lore.kernel.org/r/20240325233940.7154-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

25 files changed, 648 insertions, 137 deletions

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index e9154ace80ff..b67454b45a49 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -89,6 +89,10 @@ ifneq ($(EXTRA_LDFLAGS),)
 LDFLAGS += $(EXTRA_LDFLAGS)
 endif
 
+HOST_CFLAGS := $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\
+		$(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS)))
+HOST_LDFLAGS := $(LDFLAGS)
+
 INSTALL ?= install
 RM ?= rm -f
 
@@ -178,12 +182,9 @@ ifeq ($(filter -DHAVE_LLVM_SUPPORT -DHAVE_LIBBFD_SUPPORT,$(CFLAGS)),)
   SRCS := $(filter-out jit_disasm.c,$(SRCS))
 endif
 
-HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\
-		$(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS)))
-
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
 
-BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
+BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o)
 $(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP)
 
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
@@ -231,14 +232,11 @@ endif
 
 CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)
 
-$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
-	$(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@
-
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
 
 $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
-	$(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
+	$(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(HOST_LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
 
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 4fa4ade1ce74..3ce277544c24 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -1131,7 +1131,8 @@ static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj)
 			continue;
 		codegen("\
 			\n\
-				obj->struct_ops.%1$s = bpf_map__initial_value(obj->maps.%1$s, NULL);\n\
+				obj->struct_ops.%1$s = (typeof(obj->struct_ops.%1$s))\n\
+					bpf_map__initial_value(obj->maps.%1$s, NULL);\n\
 			\n\
 			", ident);
 	}
diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index 00c77edb6331..9b898571b49e 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -101,7 +101,6 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 	char buf[4096 / sizeof(*e) * sizeof(*e)];
 	struct pid_iter_bpf *skel;
 	int err, ret, fd = -1, i;
-	libbpf_print_fn_t default_print;
 
 	*map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL);
 	if (IS_ERR(*map)) {
@@ -118,12 +117,18 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 
 	skel->rodata->obj_type = type;
 
-	/* we don't want output polluted with libbpf errors if bpf_iter is not
-	 * supported
-	 */
-	default_print = libbpf_set_print(libbpf_print_none);
-	err = pid_iter_bpf__load(skel);
-	libbpf_set_print(default_print);
+	if (!verifier_logs) {
+		libbpf_print_fn_t default_print;
+
+		/* Unless debug information is on, we don't want the output to
+		 * be polluted with libbpf errors if bpf_iter is not supported.
+		 */
+		default_print = libbpf_set_print(libbpf_print_none);
+		err = pid_iter_bpf__load(skel);
+		libbpf_set_print(default_print);
+	} else {
+		err = pid_iter_bpf__load(skel);
+	}
 	if (err) {
 		/* too bad, kernel doesn't support BPF iterators yet */
 		err = 0;
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index 26004f0c5a6a..7bdbcac3cf62 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -102,8 +102,8 @@ int iter(struct bpf_iter__task_file *ctx)
 				       BPF_LINK_TYPE_PERF_EVENT___local)) {
 		struct bpf_link *link = (struct bpf_link *) file->private_data;
 
-		if (link->type == bpf_core_enum_value(enum bpf_link_type___local,
-						      BPF_LINK_TYPE_PERF_EVENT___local)) {
+		if (BPF_CORE_READ(link, type) == bpf_core_enum_value(enum bpf_link_type___local,
+								     BPF_LINK_TYPE_PERF_EVENT___local)) {
 			e.has_bpf_cookie = true;
 			e.bpf_cookie = get_bpf_cookie(link);
 		}
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 7b65566f3e42..8a63a9913495 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -58,6 +58,10 @@
 #define noinline
 #endif
 
+#ifndef __nocf_check
+#define __nocf_check __attribute__((nocf_check))
+#endif
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c42b9f1bada..9585f5345353 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1662,8 +1662,10 @@ union bpf_attr {
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
-		__u64 name;
-		__u32 prog_fd;
+		__u64		name;
+		__u32		prog_fd;
+		__u32		:32;
+		__aligned_u64	cookie;
 	} raw_tracepoint;
 
 	struct { /* anonymous struct for BPF_BTF_LOAD */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 97ec005c3c47..c9f4e04f38fe 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -785,6 +785,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, uprobe_multi))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_TRACE_RAW_TP:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
@@ -1173,20 +1174,31 @@ int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info
 	return bpf_obj_get_info_by_fd(link_fd, info, info_len);
 }
 
-int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_raw_tp_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
-	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
+	attr.raw_tracepoint.name = ptr_to_u64(OPTS_GET(opts, tp_name, NULL));
+	attr.raw_tracepoint.cookie = OPTS_GET(opts, cookie, 0);
 
 	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
+int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+{
+	LIBBPF_OPTS(bpf_raw_tp_opts, opts, .tp_name = name);
+
+	return bpf_raw_tracepoint_open_opts(prog_fd, &opts);
+}
+
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index df0db2f0cdb7..972e17ec0c09 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -617,6 +617,15 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 
+struct bpf_raw_tp_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const char *tp_name;
+	__u64 cookie;
+	size_t :0;
+};
+#define bpf_raw_tp_opts__last_field cookie
+
+LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index efab29b8935b..8eb2cd4ef288 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1132,8 +1132,26 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 		const char *mname;
 
 		mname = btf__name_by_offset(btf, member->name_off);
+		moff = member->offset / 8;
+		mdata = data + moff;
+		msize = btf__resolve_size(btf, member->type);
+		if (msize < 0) {
+			pr_warn("struct_ops init_kern %s: failed to resolve the size of member %s\n",
+				map->name, mname);
+			return msize;
+		}
+
 		kern_member = find_member_by_name(kern_btf, kern_type, mname);
 		if (!kern_member) {
+			/* Skip all zeros or null fields if they are not
+			 * presented in the kernel BTF.
+			 */
+			if (libbpf_is_mem_zeroed(mdata, msize)) {
+				pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n",
+					map->name, mname);
+				continue;
+			}
+
 			pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
 				map->name, mname);
 			return -ENOTSUP;
@@ -1147,10 +1165,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 			return -ENOTSUP;
 		}
 
-		moff = member->offset / 8;
 		kern_moff = kern_member->offset / 8;
-
-		mdata = data + moff;
 		kern_mdata = kern_data + kern_moff;
 
 		mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
@@ -1230,9 +1245,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 			continue;
 		}
 
-		msize = btf__resolve_size(btf, mtype_id);
 		kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
-		if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+		if (kern_msize < 0 || msize != kern_msize) {
 			pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
 				map->name, mname, (ssize_t)msize,
 				(ssize_t)kern_msize);
@@ -7317,9 +7331,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL, *tmp;
-	int btf_fd, ret, err;
 	bool own_log_buf = true;
 	__u32 log_level = prog->log_level;
+	int ret, err;
 
 	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
 		/*
@@ -7343,9 +7357,8 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = btf__fd(obj->btf);
-	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
-		load_attr.prog_btf_fd = btf_fd;
+	if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
+		load_attr.prog_btf_fd = btf__fd(obj->btf);
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
 		load_attr.func_info_cnt = prog->func_info_cnt;
@@ -8559,6 +8572,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 		return libbpf_err(-EINVAL);
 	}
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't pin BPF map without FD (was it created?)\n", map->name);
+		return libbpf_err(-EINVAL);
+	}
+
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
@@ -9294,6 +9312,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT),
+	SEC_DEF("sk_skb/verdict",	SK_SKB, BPF_SK_SKB_VERDICT, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
 	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT),
 	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT),
@@ -10303,6 +10322,11 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 		return -EINVAL;
 	}
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name);
+		return -EINVAL;
+	}
+
 	if (!check_value_sz)
 		return 0;
 
@@ -10415,8 +10439,15 @@ long libbpf_get_error(const void *ptr)
 int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
 {
 	int ret;
+	int prog_fd = bpf_program__fd(prog);
 
-	ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't use BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err(-EINVAL);
+	}
+
+	ret = bpf_link_update(bpf_link__fd(link), prog_fd, NULL);
 	return libbpf_err_errno(ret);
 }
 
@@ -10610,7 +10641,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p
 	}
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
 			prog->name);
 		return libbpf_err_ptr(-EINVAL);
 	}
@@ -11334,6 +11365,13 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 	if (!OPTS_VALID(opts, bpf_kprobe_multi_opts))
 		return libbpf_err_ptr(-EINVAL);
 
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	syms    = OPTS_GET(opts, syms, false);
 	addrs   = OPTS_GET(opts, addrs, false);
 	cnt     = OPTS_GET(opts, cnt, false);
@@ -11374,7 +11412,6 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 	}
 	link->detach = &bpf_link__detach_fd;
 
-	prog_fd = bpf_program__fd(prog);
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts);
 	if (link_fd < 0) {
 		err = -errno;
@@ -11757,6 +11794,13 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 	if (!OPTS_VALID(opts, bpf_uprobe_multi_opts))
 		return libbpf_err_ptr(-EINVAL);
 
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	syms = OPTS_GET(opts, syms, NULL);
 	offsets = OPTS_GET(opts, offsets, NULL);
 	ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL);
@@ -11832,7 +11876,6 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 	}
 	link->detach = &bpf_link__detach_fd;
 
-	prog_fd = bpf_program__fd(prog);
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts);
 	if (link_fd < 0) {
 		err = -errno;
@@ -12076,7 +12119,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (bpf_program__fd(prog) < 0) {
-		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
 			prog->name);
 		return libbpf_err_ptr(-EINVAL);
 	}
@@ -12267,13 +12310,19 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin
 	return libbpf_get_error(*link);
 }
 
-struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
-						    const char *tp_name)
+struct bpf_link *
+bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog,
+					const char *tp_name,
+					struct bpf_raw_tracepoint_opts *opts)
 {
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_opts);
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
 	int prog_fd, pfd;
 
+	if (!OPTS_VALID(opts, bpf_raw_tracepoint_opts))
+		return libbpf_err_ptr(-EINVAL);
+
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
@@ -12285,7 +12334,9 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
-	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
+	raw_opts.tp_name = tp_name;
+	raw_opts.cookie = OPTS_GET(opts, cookie, 0);
+	pfd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_opts);
 	if (pfd < 0) {
 		pfd = -errno;
 		free(link);
@@ -12297,6 +12348,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 	return link;
 }
 
+struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
+						    const char *tp_name)
+{
+	return bpf_program__attach_raw_tracepoint_opts(prog, tp_name, NULL);
+}
+
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	static const char *const prefixes[] = {
@@ -12658,6 +12715,12 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 	if (!prog->sec_def || !prog->sec_def->prog_attach_fn)
 		return libbpf_err_ptr(-EOPNOTSUPP);
 
+	if (bpf_program__fd(prog) < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link);
 	if (err)
 		return libbpf_err_ptr(err);
@@ -12698,8 +12761,13 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 	__u32 zero = 0;
 	int err, fd;
 
-	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+	if (!bpf_map__is_struct_ops(map))
+		return libbpf_err_ptr(-EINVAL);
+
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name);
 		return libbpf_err_ptr(-EINVAL);
+	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
@@ -12747,9 +12815,14 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	__u32 zero = 0;
 	int err;
 
-	if (!bpf_map__is_struct_ops(map) || !map_is_created(map))
+	if (!bpf_map__is_struct_ops(map))
 		return -EINVAL;
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name);
+		return -EINVAL;
+	}
+
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
 	/* Ensure the type of a link is correct */
 	if (st_ops_link->map_fd < 0)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7b510761f545..f88ab50c0229 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -760,9 +760,20 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
+struct bpf_raw_tracepoint_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u64 cookie;
+	size_t :0;
+};
+#define bpf_raw_tracepoint_opts__last_field cookie
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog,
+					const char *tp_name,
+					struct bpf_raw_tracepoint_opts *opts);
 
 struct bpf_trace_opts {
 	/* size of this struct, for forward/backward compatibility */
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 86804fd90dd1..51732ecb1385 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -410,6 +410,8 @@ LIBBPF_1.3.0 {
 
 LIBBPF_1.4.0 {
 	global:
+		bpf_program__attach_raw_tracepoint_opts;
+		bpf_raw_tracepoint_open_opts;
 		bpf_token_create;
 		btf__new_split;
 		btf_ext__raw_data;
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
index b36de42ee4d9..e2ff8ea1cb79 100644
--- a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
@@ -186,7 +186,7 @@ static void *task_producer(void *input)
 
 		for (i = 0; i < batch_sz; i++) {
 			if (!pthd_results[i])
-				pthread_join(pthds[i], NULL);;
+				pthread_join(pthds[i], NULL);
 		}
 	}
 
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index ace0d1011a8e..d66eddacd642 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -1,15 +1,47 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <unistd.h>
 #include "bench.h"
 #include "trigger_bench.skel.h"
 #include "trace_helpers.h"
 
+/* adjust slot shift in inc_hits() if changing */
+#define MAX_BUCKETS 256
+
+#pragma GCC diagnostic ignored "-Wattributes"
+
 /* BPF triggering benchmarks */
 static struct trigger_ctx {
 	struct trigger_bench *skel;
 } ctx;
 
-static struct counter base_hits;
+static struct counter base_hits[MAX_BUCKETS];
+
+static __always_inline void inc_counter(struct counter *counters)
+{
+	static __thread int tid = 0;
+	unsigned slot;
+
+	if (unlikely(tid == 0))
+		tid = syscall(SYS_gettid);
+
+	/* multiplicative hashing, it's fast */
+	slot = 2654435769U * tid;
+	slot >>= 24;
+
+	atomic_inc(&base_hits[slot].value); /* use highest byte as an index */
+}
+
+static long sum_and_reset_counters(struct counter *counters)
+{
+	int i;
+	long sum = 0;
+
+	for (i = 0; i < MAX_BUCKETS; i++)
+		sum += atomic_swap(&counters[i].value, 0);
+	return sum;
+}
 
 static void trigger_validate(void)
 {
@@ -23,14 +55,14 @@ static void *trigger_base_producer(void *input)
 {
 	while (true) {
 		(void)syscall(__NR_getpgid);
-		atomic_inc(&base_hits.value);
+		inc_counter(base_hits);
 	}
 	return NULL;
 }
 
 static void trigger_base_measure(struct bench_res *res)
 {
-	res->hits = atomic_swap(&base_hits.value, 0);
+	res->hits = sum_and_reset_counters(base_hits);
 }
 
 static void *trigger_producer(void *input)
@@ -42,7 +74,7 @@ static void *trigger_producer(void *input)
 
 static void trigger_measure(struct bench_res *res)
 {
-	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+	res->hits = sum_and_reset_counters(ctx.skel->bss->hits);
 }
 
 static void setup_ctx(void)
@@ -137,7 +169,7 @@ static void trigger_fmodret_setup(void)
  * GCC doesn't generate stack setup preample for these functions due to them
  * having no input arguments and doing nothing in the body.
  */
-__weak void uprobe_target_nop(void)
+__nocf_check __weak void uprobe_target_nop(void)
 {
 	asm volatile ("nop");
 }
@@ -146,7 +178,7 @@ __weak void opaque_noop_func(void)
 {
 }
 
-__weak int uprobe_target_push(void)
+__nocf_check __weak int uprobe_target_push(void)
 {
 	/* overhead of function call is negligible compared to uprobe
 	 * triggering, so this shouldn't affect benchmark results much
@@ -155,7 +187,7 @@ __weak int uprobe_target_push(void)
 	return 1;
 }
 
-__weak void uprobe_target_ret(void)
+__nocf_check __weak void uprobe_target_ret(void)
 {
 	asm volatile ("");
 }
@@ -164,7 +196,7 @@ static void *uprobe_base_producer(void *input)
 {
 	while (true) {
 		uprobe_target_nop();
-		atomic_inc(&base_hits.value);
+		inc_counter(base_hits);
 	}
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 1454cebc262b..4407ea428e77 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -573,6 +573,115 @@ cleanup:
 		close(lsm_fd);
 }
 
+static void tp_btf_subtest(struct test_bpf_cookie *skel)
+{
+	__u64 cookie;
+	int prog_fd, link_fd = -1;
+	struct bpf_link *link = NULL;
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
+	LIBBPF_OPTS(bpf_trace_opts, trace_opts);
+
+	/* There are three different ways to attach tp_btf (BTF-aware raw
+	 * tracepoint) programs. Let's test all of them.
+	 */
+	prog_fd = bpf_program__fd(skel->progs.handle_tp_btf);
+
+	/* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */
+	skel->bss->tp_btf_res = 0;
+
+	raw_tp_opts.cookie = cookie = 0x11000000000000L;
+	link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "raw_tp_open_res");
+
+	/* low-level generic bpf_link_create() API */
+	skel->bss->tp_btf_res = 0;
+
+	link_opts.tracing.cookie = cookie = 0x22000000000000L;
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_RAW_TP, &link_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_link_create"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "link_create_res");
+
+	/* high-level bpf_link-based bpf_program__attach_trace_opts() API */
+	skel->bss->tp_btf_res = 0;
+
+	trace_opts.cookie = cookie = 0x33000000000000L;
+	link = bpf_program__attach_trace_opts(skel->progs.handle_tp_btf, &trace_opts);
+	if (!ASSERT_OK_PTR(link, "attach_trace_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	bpf_link__destroy(link); /* detach */
+	link = NULL;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "attach_trace_opts_res");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	bpf_link__destroy(link);
+}
+
+static void raw_tp_subtest(struct test_bpf_cookie *skel)
+{
+	__u64 cookie;
+	int prog_fd, link_fd = -1;
+	struct bpf_link *link = NULL;
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
+	LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts);
+
+	/* There are two different ways to attach raw_tp programs */
+	prog_fd = bpf_program__fd(skel->progs.handle_raw_tp);
+
+	/* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */
+	skel->bss->raw_tp_res = 0;
+
+	raw_tp_opts.tp_name = "sys_enter";
+	raw_tp_opts.cookie = cookie = 0x55000000000000L;
+	link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->raw_tp_res, cookie, "raw_tp_open_res");
+
+	/* high-level bpf_link-based bpf_program__attach_raw_tracepoint_opts() API */
+	skel->bss->raw_tp_res = 0;
+
+	opts.cookie = cookie = 0x66000000000000L;
+	link = bpf_program__attach_raw_tracepoint_opts(skel->progs.handle_raw_tp,
+						       "sys_enter", &opts);
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	bpf_link__destroy(link); /* detach */
+	link = NULL;
+
+	ASSERT_EQ(skel->bss->raw_tp_res, cookie, "attach_raw_tp_opts_res");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	bpf_link__destroy(link);
+}
+
 void test_bpf_cookie(void)
 {
 	struct test_bpf_cookie *skel;
@@ -601,6 +710,9 @@ void test_bpf_cookie(void)
 		tracing_subtest(skel);
 	if (test__start_subtest("lsm"))
 		lsm_subtest(skel);
-
+	if (test__start_subtest("tp_btf"))
+		tp_btf_subtest(skel);
+	if (test__start_subtest("raw_tp"))
+		raw_tp_subtest(skel);
 	test_bpf_cookie__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index a88e6e07e4f5..94cb22b01482 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -89,7 +89,7 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 
 	WRITE_ONCE(stop, 0);
 
-	lfd = socket(AF_INET6, SOCK_STREAM, 0);
+	lfd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_NEQ(lfd, -1, "socket"))
 		return;
 
@@ -103,21 +103,10 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
 	    settimeo(lfd, 0) || settimeo(fd, 0))
 		goto done;
 
-	/* bind, listen and start server thread to accept */
-	sa6.sin6_family = AF_INET6;
-	sa6.sin6_addr = in6addr_loopback;
-	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
-	if (!ASSERT_NEQ(err, -1, "bind"))
-		goto done;
-
 	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
 	if (!ASSERT_NEQ(err, -1, "getsockname"))
 		goto done;
 
-	err = listen(lfd, 1);
-	if (!ASSERT_NEQ(err, -1, "listen"))
-		goto done;
-
 	if (sk_stg_map) {
 		err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
 					  &expected_stg, BPF_NOEXIST);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index a8b53b8736f0..f66ceccd7029 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -25,7 +25,7 @@ static void test_lookup_update(void)
 	int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id;
 	int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd;
 	struct test_btf_map_in_map *skel;
-	int err, key = 0, val, i, fd;
+	int err, key = 0, val, i;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -102,30 +102,6 @@ static void test_lookup_update(void)
 	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
 	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
 
-	test_btf_map_in_map__destroy(skel);
-	skel = NULL;
-
-	/* we need to either wait for or force synchronize_rcu(), before
-	 * checking for "still exists" condition, otherwise map could still be
-	 * resolvable by ID, causing false positives.
-	 *
-	 * Older kernels (5.8 and earlier) freed map only after two
-	 * synchronize_rcu()s, so trigger two, to be entirely sure.
-	 */
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-
-	fd = bpf_map_get_fd_by_id(map1_id);
-	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-	fd = bpf_map_get_fd_by_id(map2_id);
-	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 24d493482ffc..e72d75d6baa7 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -12,77 +12,229 @@
 #include <sys/wait.h>
 #include <sys/mount.h>
 #include <sys/fcntl.h>
+#include "network_helpers.h"
 
 #define STACK_SIZE (1024 * 1024)
 static char child_stack[STACK_SIZE];
 
-static int test_current_pid_tgid(void *args)
+static int get_pid_tgid(pid_t *pid, pid_t *tgid,
+			struct test_ns_current_pid_tgid__bss *bss)
 {
-	struct test_ns_current_pid_tgid__bss  *bss;
-	struct test_ns_current_pid_tgid *skel;
-	int err = -1, duration = 0;
-	pid_t tgid, pid;
 	struct stat st;
+	int err;
 
-	skel = test_ns_current_pid_tgid__open_and_load();
-	if (CHECK(!skel, "skel_open_load", "failed to load skeleton\n"))
-		goto cleanup;
-
-	pid = syscall(SYS_gettid);
-	tgid = getpid();
+	*pid = syscall(SYS_gettid);
+	*tgid = getpid();
 
 	err = stat("/proc/self/ns/pid", &st);
-	if (CHECK(err, "stat", "failed /proc/self/ns/pid: %d\n", err))
-		goto cleanup;
+	if (!ASSERT_OK(err, "stat /proc/self/ns/pid"))
+		return err;
 
-	bss = skel->bss;
 	bss->dev = st.st_dev;
 	bss->ino = st.st_ino;
 	bss->user_pid = 0;
 	bss->user_tgid = 0;
+	return 0;
+}
+
+static int test_current_pid_tgid_tp(void *args)
+{
+	struct test_ns_current_pid_tgid__bss  *bss;
+	struct test_ns_current_pid_tgid *skel;
+	int ret = -1, err;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.tp_handler, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, bss))
+		goto cleanup;
 
 	err = test_ns_current_pid_tgid__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__attach"))
 		goto cleanup;
 
 	/* trigger tracepoint */
 	usleep(1);
-	ASSERT_EQ(bss->user_pid, pid, "pid");
-	ASSERT_EQ(bss->user_tgid, tgid, "tgid");
-	err = 0;
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
+
+cleanup:
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
+}
+
+static int test_current_pid_tgid_cgrp(void *args)
+{
+	struct test_ns_current_pid_tgid__bss *bss;
+	struct test_ns_current_pid_tgid *skel;
+	int server_fd = -1, ret = -1, err;
+	int cgroup_fd = *(int *)args;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.cgroup_bind4, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, bss))
+		goto cleanup;
+
+	skel->links.cgroup_bind4 = bpf_program__attach_cgroup(
+		skel->progs.cgroup_bind4, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.cgroup_bind4, "bpf_program__attach_cgroup"))
+		goto cleanup;
+
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
 
 cleanup:
-	 test_ns_current_pid_tgid__destroy(skel);
+	if (server_fd >= 0)
+		close(server_fd);
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
+}
+
+static int test_current_pid_tgid_sk_msg(void *args)
+{
+	int verdict, map, server_fd = -1, client_fd = -1;
+	struct test_ns_current_pid_tgid__bss *bss;
+	static const char send_msg[] = "message";
+	struct test_ns_current_pid_tgid *skel;
+	int ret = -1, err, key = 0;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.sk_msg, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, skel->bss))
+		goto cleanup;
+
+	verdict = bpf_program__fd(skel->progs.sk_msg);
+	map = bpf_map__fd(skel->maps.sock_map);
+	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "prog_attach"))
+		goto cleanup;
+
+	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
+		goto cleanup;
 
-	return err;
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto cleanup;
+
+	err = bpf_map_update_elem(map, &key, &client_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto cleanup;
+
+	err = send(client_fd, send_msg, sizeof(send_msg), 0);
+	if (!ASSERT_EQ(err, sizeof(send_msg), "send(msg)"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
+
+cleanup:
+	if (server_fd >= 0)
+		close(server_fd);
+	if (client_fd >= 0)
+		close(client_fd);
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
 }
 
-static void test_ns_current_pid_tgid_new_ns(void)
+static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg)
 {
-	int wstatus, duration = 0;
+	int wstatus;
 	pid_t cpid;
 
 	/* Create a process in a new namespace, this process
 	 * will be the init process of this new namespace hence will be pid 1.
 	 */
-	cpid = clone(test_current_pid_tgid, child_stack + STACK_SIZE,
-		     CLONE_NEWPID | SIGCHLD, NULL);
+	cpid = clone(fn, child_stack + STACK_SIZE,
+		     CLONE_NEWPID | SIGCHLD, arg);
 
-	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
+	if (!ASSERT_NEQ(cpid, -1, "clone"))
 		return;
 
-	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
+	if (!ASSERT_NEQ(waitpid(cpid, &wstatus, 0), -1, "waitpid"))
 		return;
 
-	if (CHECK(WEXITSTATUS(wstatus) != 0, "newns_pidtgid", "failed"))
+	if (!ASSERT_OK(WEXITSTATUS(wstatus), "newns_pidtgid"))
 		return;
 }
 
+static void test_in_netns(int (*fn)(void *), void *arg)
+{
+	struct nstoken *nstoken = NULL;
+
+	SYS(cleanup, "ip netns add ns_current_pid_tgid");
+	SYS(cleanup, "ip -net ns_current_pid_tgid link set dev lo up");
+
+	nstoken = open_netns("ns_current_pid_tgid");
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto cleanup;
+
+	test_ns_current_pid_tgid_new_ns(fn, arg);
+
+cleanup:
+	if (nstoken)
+		close_netns(nstoken);
+	SYS_NOFAIL("ip netns del ns_current_pid_tgid");
+}
+
 /* TODO: use a different tracepoint */
 void serial_test_ns_current_pid_tgid(void)
 {
-	if (test__start_subtest("ns_current_pid_tgid_root_ns"))
-		test_current_pid_tgid(NULL);
-	if (test__start_subtest("ns_current_pid_tgid_new_ns"))
-		test_ns_current_pid_tgid_new_ns();
+	if (test__start_subtest("root_ns_tp"))
+		test_current_pid_tgid_tp(NULL);
+	if (test__start_subtest("new_ns_tp"))
+		test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL);
+	if (test__start_subtest("new_ns_cgrp")) {
+		int cgroup_fd = -1;
+
+		cgroup_fd = test__join_cgroup("/sock_addr");
+		if (ASSERT_GE(cgroup_fd, 0, "join_cgroup")) {
+			test_in_netns(test_current_pid_tgid_cgrp, &cgroup_fd);
+			close(cgroup_fd);
+		}
+	}
+	if (test__start_subtest("new_ns_sk_msg"))
+		test_in_netns(test_current_pid_tgid_sk_msg, NULL);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
index ee5372c7f2c7..098776d00ab4 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
@@ -93,9 +93,56 @@ cleanup:
 	struct_ops_module__destroy(skel);
 }
 
+static void test_struct_ops_not_zeroed(void)
+{
+	struct struct_ops_module *skel;
+	int err;
+
+	/* zeroed is 0, and zeroed_op is null */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open"))
+		return;
+
+	err = struct_ops_module__load(skel);
+	ASSERT_OK(err, "struct_ops_module_load");
+
+	struct_ops_module__destroy(skel);
+
+	/* zeroed is not 0 */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed"))
+		return;
+
+	/* libbpf should reject the testmod_zeroed since struct
+	 * bpf_testmod_ops in the kernel has no "zeroed" field and the
+	 * value of "zeroed" is non-zero.
+	 */
+	skel->struct_ops.testmod_zeroed->zeroed = 0xdeadbeef;
+	err = struct_ops_module__load(skel);
+	ASSERT_ERR(err, "struct_ops_module_load_not_zeroed");
+
+	struct_ops_module__destroy(skel);
+
+	/* zeroed_op is not null */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed_op"))
+		return;
+
+	/* libbpf should reject the testmod_zeroed since the value of its
+	 * "zeroed_op" is not null.
+	 */
+	skel->struct_ops.testmod_zeroed->zeroed_op = skel->progs.test_3;
+	err = struct_ops_module__load(skel);
+	ASSERT_ERR(err, "struct_ops_module_load_not_zeroed_op");
+
+	struct_ops_module__destroy(skel);
+}
+
 void serial_test_struct_ops_module(void)
 {
 	if (test__start_subtest("test_struct_ops_load"))
 		test_struct_ops_load();
+	if (test__start_subtest("test_struct_ops_not_zeroed"))
+		test_struct_ops_not_zeroed();
 }
 
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 3db416606f2f..fe65e0952a1e 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -673,7 +673,7 @@ static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul)
 
 static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n)
 {
-	int *t, i, sum = 0;;
+	int *t, i, sum = 0;
 
 	while ((t = bpf_iter_num_next(it))) {
 		i = *t;
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c
index 026cabfa7f1f..86e1e50c5531 100644
--- a/tools/testing/selftests/bpf/progs/struct_ops_module.c
+++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c
@@ -23,7 +23,7 @@ void BPF_PROG(test_2, int a, int b)
 	test_2_result = a + b;
 }
 
-SEC("struct_ops/test_3")
+SEC("?struct_ops/test_3")
 int BPF_PROG(test_3, int a, int b)
 {
 	test_2_result = a + b + 3;
@@ -54,3 +54,17 @@ struct bpf_testmod_ops___v2 testmod_2 = {
 	.test_1 = (void *)test_1,
 	.test_2 = (void *)test_2_v2,
 };
+
+struct bpf_testmod_ops___zeroed {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+	void (*zeroed_op)(int a, int b);
+	int zeroed;
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___zeroed testmod_zeroed = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2_v2,
+};
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
index 5a3a80f751c4..c83142b55f47 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
@@ -15,6 +15,8 @@ __u64 uprobe_res;
 __u64 uretprobe_res;
 __u64 tp_res;
 __u64 pe_res;
+__u64 raw_tp_res;
+__u64 tp_btf_res;
 __u64 fentry_res;
 __u64 fexit_res;
 __u64 fmod_ret_res;
@@ -87,6 +89,20 @@ int handle_pe(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("raw_tp/sys_enter")
+int handle_raw_tp(void *ctx)
+{
+	update(ctx, &raw_tp_res);
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int handle_tp_btf(void *ctx)
+{
+	update(ctx, &tp_btf_res);
+	return 0;
+}
+
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(fentry_test1, int a)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
index 0763d49f9c42..386315afad65 100644
--- a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
@@ -5,23 +5,48 @@
 #include <stdint.h>
 #include <bpf/bpf_helpers.h>
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u32);
+} sock_map SEC(".maps");
+
 __u64 user_pid = 0;
 __u64 user_tgid = 0;
 __u64 dev = 0;
 __u64 ino = 0;
 
-SEC("tracepoint/syscalls/sys_enter_nanosleep")
-int handler(const void *ctx)
+static void get_pid_tgid(void)
 {
 	struct bpf_pidns_info nsdata;
 
 	if (bpf_get_ns_current_pid_tgid(dev, ino, &nsdata, sizeof(struct bpf_pidns_info)))
-		return 0;
+		return;
 
 	user_pid = nsdata.pid;
 	user_tgid = nsdata.tgid;
+}
 
+SEC("?tracepoint/syscalls/sys_enter_nanosleep")
+int tp_handler(const void *ctx)
+{
+	get_pid_tgid();
 	return 0;
 }
 
+SEC("?cgroup/bind4")
+int cgroup_bind4(struct bpf_sock_addr *ctx)
+{
+	get_pid_tgid();
+	return 1;
+}
+
+SEC("?sk_msg")
+int sk_msg(struct sk_msg_md *msg)
+{
+	get_pid_tgid();
+	return SK_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 5fda43901033..42ec202015ed 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -9,12 +9,27 @@
 
 char _license[] SEC("license") = "GPL";
 
-long hits = 0;
+#define CPU_MASK 255
+#define MAX_CPUS (CPU_MASK + 1) /* should match MAX_BUCKETS in benchs/bench_trigger.c */
+
+/* matches struct counter in bench.h */
+struct counter {
+	long value;
+} __attribute__((aligned(128)));
+
+struct counter hits[MAX_CPUS];
+
+static __always_inline void inc_counter(void)
+{
+	int cpu = bpf_get_smp_processor_id();
+
+	__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
+}
 
 SEC("tp/syscalls/sys_enter_getpgid")
 int bench_trigger_tp(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
@@ -22,69 +37,69 @@ SEC("raw_tp/sys_enter")
 int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
 {
 	if (id == __NR_getpgid)
-		__sync_add_and_fetch(&hits, 1);
+		inc_counter();
 	return 0;
 }
 
 SEC("kprobe/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kretprobe/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kretprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kprobe.multi/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kprobe_multi(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kretprobe.multi/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kretprobe_multi(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fexit/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fexit(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry_sleep(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fmod_ret/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fmodret(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return -22;
 }
 
 SEC("uprobe")
 int bench_trigger_uprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index f4936834f76f..dde0bb16e782 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -7,6 +7,7 @@
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include "test_core_extern.skel.h"
+#include "struct_ops_module.skel.h"
 
 template <typename T>
 class Skeleton {
@@ -98,6 +99,7 @@ int main(int argc, char *argv[])
 {
 	struct btf_dump_opts opts = { };
 	struct test_core_extern *skel;
+	struct struct_ops_module *skel2;
 	struct btf *btf;
 	int fd;
 
@@ -118,6 +120,9 @@ int main(int argc, char *argv[])
 	skel = test_core_extern__open_and_load();
 	test_core_extern__destroy(skel);
 
+	skel2 = struct_ops_module__open_and_load();
+	struct_ops_module__destroy(skel2);
+
 	fd = bpf_enable_stats(BPF_STATS_RUN_TIME);
 	if (fd < 0)
 		std::cout << "FAILED to enable stats: " << fd << std::endl;
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index 910044f08908..7989ec608454 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -72,7 +72,6 @@ cleanup() {
 server_listen() {
 	ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" &
 	server_pid=$!
-	sleep 0.2
 }
 
 client_connect() {
@@ -93,6 +92,16 @@ verify_data() {
 	fi
 }
 
+wait_for_port() {
+	for i in $(seq 20); do
+		if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then
+			return 0
+		fi
+		sleep 0.1
+	done
+	return 1
+}
+
 set -e
 
 # no arguments: automated test, run all
@@ -193,6 +202,7 @@ setup
 # basic communication works
 echo "test basic connectivity"
 server_listen
+wait_for_port ${port} ${netcat_opt}
 client_connect
 verify_data
 
@@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \
 	section "encap_${tuntype}_${mac}"
 echo "test bpf encap without decap (expect failure)"
 server_listen
+wait_for_port ${port} ${netcat_opt}
 ! client_connect
 
 if [[ "$tuntype" =~ "udp" ]]; then